Katerina Zanos

Cohort 2

Cohort 1

Engineers and engineering leaders who build, deploy, and scale software systems.

Data scientists who apply statistical and ML techniques to extract insights from data.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Building, training, and deploying machine learning models — from classical ML to deep learning.

Designing scalable, reliable software systems — architecture patterns, distributed systems, and technical tradeoffs.

Learn to design and evaluate a production-ready media recommender: metrics, architecture, cold start, and drafting an effective roadmap.

Principal ML Engineer @ Disney, ex-Meta

Principal ML Engineer @ Disney, x-Meta, x-NYT

Production-Ready Recommenders for Media Products

Sr. Machine Learning Engineer

AI Engineer

Product Manager

Product Owner 

The New York Times

The Walt Disney Company

ESPN

Columbia University

Build a production-ready Recommender System Blueprint for a media surface of your choice. This will be an artifact you can take back to work to guide implementation, align stakeholders, and make smarter roadmap calls.Most teams working on recommender systems don’t struggle because they lack algorithms. They struggle because they lack a practical, end-to-end playbook for shipping.You might know the building blocks (embeddings, retrieval, ranking, bandits), but still feel stuck on the hard parts:<ul><li>which metrics actually reflect what product wants</li><li>how to architect the system from logging to serving</li><li>what model to choose under real constraints</li><li>how to handle cold start and sparse data</li><li>and how to prove ML is worth it over heuristics</li></ul>I’ve built recommendation systems in production across news, feeds, and sports over the last 10 years (NYT, Meta, ESPN). This course turns that experience into a clear, reusable process you can apply to your own product without needing FAANG-scale infrastructure. By the end, you’ll be able to confidently design and evaluate production-ready recommenders, defend trade-offs, and use your Blueprint as a durable reference for future iterations.

Design and evaluate a media recommender system that ships to production.

Build a real-world mental model of recommenders (not just algorithms)

Design metrics and success criteria your team will actually align on

Architect the system: make the right calls on retrieval, ranking, and serving

Handle cold start with pragmatic strategies

Know when ML beats heuristics and how to prove it

You are able to interpret (not compute) common product metrics like retention/engagement and discuss tradeoffs.

Metric + product reasoning at a basic level

You can follow an architecture diagram and understand concepts like services/APIs, latency, reliability constraints.

Ability to follow system-level thinking

We will be working with specs, diagrams, and decision frameworks (not code).

Comfort making structured decisions from imperfect data

Senior ML Engineers &amp; Data Scientists who can build models but want sharper judgment on what to build next and how to defend it

Software Engineers transitioning into ML who want to think in systems + measurement, not just training code.

Tech Leads who need an end-to-end playbook to review designs, align metrics with product, and avoid expensive detours.

Learn directly from Katerina Zanos

Katerina Zanos

Courses

Production-Ready Recommenders for Media Products

Lightning Lessons

Kickstart Your Recommender System

How to Design a Metrics-First Recommender System